Application of self-adaptive technology of power automation equipment in power system relay protection Chen Hao (Department of Electric Power, Sichuan University, Chengdu 610065, China). Using communication networks to acquire and apply fault information more flexibly, applying artificial intelligence technology to fault information processing relay protection devices is expected to obtain stronger self-adaptive capabilities, thereby significantly improving its performance.
EleetroniePublishi has always been concerned with the unbalanced output of movement criteria. In recent years, artificial intelligence technologies such as neural networks and fuzzy logic have been applied in various fields of power systems, and research in the field of relay protection has begun. Make full use of artificial intelligence technology to use appropriate communication network to obtain more fault information, relay protection device is expected to obtain a stronger self-adaptive ability, thereby significantly improving its performance.
1 Application of adaptive technology in relay protection Adaptive relay protection is a research project put forward in the 1980s. A new scheme has been proposed: On the microcomputer protection platform, the auxiliary contacts of the knife switch are mainly used, and the load current is based on each unit. The calculation checks the correctness of the auxiliary contact of the switch and automatically corrects the error. Each pair of knife gates still introduces a pair of contact points. The instantaneous value of the current is calculated by the microcomputer in real time. According to the current criterion, the steady state and transient judgment are combined to find and correct the error of the auxiliary contact in real time so as to realize the bus operation mode self-adaptation. The new scheme will improve the accuracy of the busbar protection operation.
1.1.2 Realizing Adaptive Functions Using Real-Time Information of Protected Components Another type of information is information directly related to the protected electrical components. Most of the traditional relay protection devices use the real-time fault information obtained by the protection installation to identify faults. For its rational use, it can also obtain better adaptive motion characteristics.
In general, the current trip protection action value is determined by tripping the three-phase short-circuit fault current at the end of the line. When a two-phase short circuit occurs, the sensitivity of the protection action is greatly reduced. After adopting the adaptive technology, when the fault occurs, the protection first discriminates the system operation mode and fault type, and then adaptively adjusts the current protection action value according to different fault types, thereby greatly improving the sensitivity of the protection action. A basic method for implementing adaptive current quick-break protection is proposed. The setting value of the current quick-break protection should be changed with the actual conditions of the power system operation mode and the short-circuit fault type. In order to realize the self-adaptive setting of the current quick-break, the short-circuit fault type and the system equivalent impedance must be determined in real time. The adaptive treatment of the short-circuit fault type and the system operating mode needs to be considered separately.
In the adaptive over-current protection, the protection action value is set to the fixed threshold and the adaptive floating threshold 2 part. After adaptive floating threshold and adaptive floating threshold, protection has higher sensitivity in different types of faults. Discussed the protection startup mode of fault components. In normal operation, the fault component also has an unbalanced output. Take the maximum value of unbalanced output in the previous cycle as the adaptive floating threshold of the fault startup criterion, then the fixed threshold can be greatly reduced. For example, taking the line rated current as 10%, the sensitivity of protection startup can be greatly improved. .
The direct use of the third harmonic voltage of the generator terminal and the neutral point can reflect the earth fault near the neutral point of the generator; however, the earthing protection of the third harmonic voltage is related to the working conditions of the generator during normal operation. There is a phenomenon that the protection sensitivity is not enough and the incorrect operation rate is high. An adaptive third-harmonic voltage generator stator grounding protection principle is proposed to protect the third harmonic in real-time automatic tracking. The change of the normal operation mode of the generator and the third harmonic voltage and its ratio change caused by the system oscillation are much slower than the change of the generator stator ground fault. Using adaptive microcomputer protection can automatically track this slow change. , thereby greatly improving the protection sensitivity.
1.1.3 Implementation of adaptive functions using substation integrated information The development of substation automation systems provides the conditions for realizing comprehensive utilization of real-time information in the entire substation. This kind of information includes not only the switch information and the real-time current and voltage information on each electrical component, but also the action information of each electrical component protection. A comprehensive analysis of the protective action behavior of relay protection devices with different principles of the same component can maximize the advantages of relay protection devices with different principles and obtain the integrated optimal operating characteristics of protection. A comprehensive analysis of the operation behavior of relay protection devices of adjacent electrical components may also achieve more reliable locking of relay protection devices for non-faulty components. On the other hand, the integrated use of substation fault information increases the redundancy of fault information, which also improves the reliability of computer relay protection. In order to realize the comprehensive utilization of the real-time information of the entire substation, fast failure information exchange technology must be adopted.
Some domestic units have begun research on distributed bus protection. Distributed bus protection uses network technology to share fault data. In the case of busbars connecting 20 outlets, the minimum data transmission rate of the channels should be estimated to be 3.52 Mbit/s. The IEEE-88 standard bus is chosen to constitute the communication network. At present, the maximum data transmission rate of the IEEE-88 bus can reach 8 Mbit/s to fully meet the requirements of distributed bus protection for data transmission rate. With the gradual application of these research results, adaptive protection can achieve its fault information integration.
The idea of ​​comprehensively using directional elements of substation line protection to implement directional busbar protection has been proposed for a long time. A line-locked directional protection system has been proposed for decentralized line treatment. The various electrical components connected to the busbar can be regarded as multi-terminal lines. At one end. Because the bus protection does not have to consider the phase selection trip, if the bus is in an open and closed place, that is, only a line is connected to the bus, the closed line protection principle is used to combine the components of the line reflecting the fault outside the zone and the fault within the zone. Bus protection can be formed. When a fault occurs on the line, the momentary contact of the faulty line segment issues a blocking signal and the busbar protection cannot be tripped. When the busbar fails, it reflects the faulty component action in the zone, and there is no blocking signal. The busbar protection operates correctly. Because it is based on perfect microcomputer line protection, the forward and reverse directional components should be able to instantaneously reflect various types of faults. This directional distributed bus bar protection has small amount of information exchanged between each bay and can pass through. Simple and reliable communication network implementation. Making full use of its own microcomputer line protection can be doubled with the double protection of line protection. The bus protection is based on the mature microcomputer line protection, which can disperse the voltage blocking quantity and has high reliability. At the same time, the bus protection will no longer be affected by TA saturation.
1.1.4 Using Remote Information to Implement Adaptive Functions With the development of grid dispatch automation, various communication methods can also be used to obtain useful additional information from neighboring substations and dispatch centers.
Of course, using communication methods to obtain far-end information requires a complete real-time communication means. The basic requirements for information transmission are mainly its real-time performance and reliability. Only real-time data transmission can complete the real-time adaptive function of relay protection; and reliable data transmission is the basic prerequisite for achieving highly reliable adaptive relay protection. It can be expected that digital communication will play an important role in this. For example, in some complicated difficult-to-identify fault conditions, fault information of neighboring substations can be used to achieve more reliable adaptive relay protection. With the development of communication technologies, new types of protection using high-speed data channels for substation fault data sharing have begun to be researched and tested.
A new solution for adaptive wide-area current differential backup protection is implemented based on the service digital network-based high-speed data channel. Using this technology, the access speed between the user and the broadband integrated service digital network will reach 155 Mbit/s, which makes it very easy to share the substation fault data. In the event of failure of the main protection, the wide-area communication network can be used to obtain the necessary fault current information, which can realize the fast action of adaptive wide-area current differential backup protection.
Bus protection is provided. The basic principle is that it is more important to use the bus as a double-end ranging from a super-ishl circuit. The bookmark1 method is applied to the double-ended ranging of transmission lines. It takes the length of the line as the horizontal distance between the towers of the line and classifies the influence of various factors on the line parameters into the change of the line parameters. With the help of double-end or multi-end communication tools, it can estimate the line parameters in real-time online in order to improve the double-end. Ranging accuracy. In dual-end ranging, the use of its own hardware equipment can effectively weaken the impact of line parameter changes on ranging accuracy. This method is applicable to various overhead power transmission lines, especially for those that cross the terrain and have a difficult climate (such as high-ice icing land). The original phase-differential current differential protection lacks flexibility in remote communication, and the proposed communication-specific and multiplexing adaptive methods overcome this deficiency. The existing differential protection mostly uses the numerical correction method to realize synchronization, and the premise is that the transmission delays in both directions are equal. In the multiplexed system applied to some elastic loads, the error is large. However, when using the global satellite positioning system (GPS) to achieve synchronization, the protection has a strong dependence on GPS. In this regard, the ideal solution is to use an adaptive synchronization method that uses the GPS clock synchronization method as the main method and the numerical correction method as the auxiliary method. Current differential uses the principle of instantaneous differential value and instantaneous value of the fault component to synthesize differential signals. Artificial neural network (ANN) is used to automatically recognize TA saturation. When it is determined that the TA is saturated, it automatically switches to the instantaneous value differential mode, and the braking coefficient is adaptively changed to improve the stability of the protection, that is, the ability to determine the status of the current transformer in real time and adaptively change the protection criteria.
The scheme for implementing an adaptive cooperative protection system using local and remote substation fault information is composed of many independent intelligent agent protection subsystems. The intelligent agent protection subsystems communicate with each other and coordinate with each other, thus adaptively reconfiguring the protection system in the event of changes in the system operation mode and failure of individual protection devices.
Protection system implementation method. According to the inherent distribution of the power system, a distributed computer system composed of computers using power dispatching systems is proposed. The distributed adaptive relay protection subsystems are constructed using plant computers and relay protection devices, and they are combined to form a large power grid. Distributed adaptive relay protection system. By knowing the mode of operation mode 1j, in the disturbance area of ​​the power system, the protection setting of the distributed adaptive relay protection subsystem is calculated off-line, decentralized, and online according to the operation mode, so that the protection setting is changed in real time. value.
1.2 Use different information processing methods to achieve adaptive function 1.21 Use fuzzy logic to achieve adaptive function The introduction of fuzzy set theory into relay protection, opened up a new path for the development of relay protection. Fuzzy theory (fuzzy theory) is a fuzzy set theory based on fuzzy set theory. It is a fuzzy set theory based on fuzzy set theory. It applies the traditional digital transformer protection various motion criteria to a certain degree of membership function through fuzzy processing; then according to the actual measured value of the fault information, the membership degree of various action criteria is determined through the fuzzy decision system. Self-adaptively determine the operating conditions of the transformer and issue action instructions. Compared with the traditional transformer protection, its motion sensitivity, selectivity and reliability have been improved. Transformer fault current and excitation current inrush method. By comparing the degree of symmetry of the actual sampling of the degree of membership function and theoretical analysis of the degree of approximation of the degree of membership function of current symmetry to achieve the fault diagnosis of the transformer. The transformer fault is judged when the fuzzy closeness is greater than a certain value.
New principle of fuzzy fault phase selection for frequency components. This principle uses the high-frequency components of voltage faults to extract three-phase voltages, uses the modulo-shifted frequency domain features based on different phases, uses fuzzy sets, and processes frequency-domain features to achieve fault phase selection, which is characterized by ultra-high speed. The fault phase selection is not affected by the transition resistance and the initial angle of the fault, and the fault phase can also be selected for the transition fault.
Automatic self-locking adaptive optimization criteria to improve the success rate of reclosing. In this paper, the ratio of capacitive coupling voltage to mutual inductance voltage is taken as the first input variable of the fuzzy controller, and the ratio of fault terminal voltage to mutual inductance voltage is taken as the second input variable of the fuzzy controller. The trip signal is the output of the fuzzy controller. This method uses the information of fault boundary conditions such as capacitive coupling voltage, mutual-inductance voltage, and fault terminal voltage, and adaptively corrects the original voltage criteria using the fuzzy controller. Theoretical analysis and dynamic model test results show that this method has a good application prospects.
Different characteristics analysis, starting from the fault characteristics, using fuzzy set theory to identify the short circuit occurred in the process of oscillation. The operation of the power system is very complicated, and the conditions of oscillation and short circuit are various. In this case, it is limited to distinguish the oscillation and the short circuit by using a precise and absolute setting according to a single criterion. . Using the fuzzy pattern recognition principle, a corresponding fuzzy mathematics model is established, which makes it possible to quickly and accurately identify three-phase short-circuits occurring at the center of oscillation when the power angle of the two-machine system is 180* in many cases unfavorable to recognition. . The article gives the corresponding fuzzy mathematics model, and through a lot of simulation experiments, get good simulation results.
1.22 Using Neural Networks to Implement Adaptive Functions 1 A method based on artificial neural networks for identifying permanent and transient failures is proposed. In the case of a transient fault, the arc extinguishing time can be determined and an adaptive single-phase reclosing can be realized. Transient faults and permanent fault voltage waveforms are different and can be used as the basis for identifying fault types. However, the actual fault voltage waveform and amplitude are affected by many factors, such as the line structure, system parameters, pre-fault load components, and so on. Using EMTP simulation, the author simulates and analyzes the fault voltage waveforms for different combinations of system parameters, fault location, pre-fault load components, and breaker opening time, and extracts the most representative feature as the neural network input. The input node is a non-fully connected BP neural network with 6 hidden nodes of 5 and output nodes of 1. A design method of adaptive single-phase reclosing based on artificial neural network is proposed. The special method of how to train neural network using fault data and how to implement it on hardware are presented.
A New Method of Self - adaptive Adjustment of Distance Protection Distance Setbacks . Due to the influence of mutual inductance, the self-adaptive adjustment of the distance protection of the double-circuit line is very difficult. The new method used is to introduce a correction factor that compensates for mutual inductance of parallel lines in the impedance setting value. Because of the nonlinear relationship between the correction factor and the system state, it is difficult to estimate using conventional methods. Therefore, a BP neural network is adopted. The parameters such as positive sequence bus voltage, positive sequence line current, load current, and double-circuit line operation mode are input to the network for online estimation. Correction factor to achieve adaptive timely adjustment of protection action value.
The implementation method was discussed and the possibility of its application in a radial distribution system was discussed. Through a large number of simulation experiments, the neural network is used to simulate the fault conditions in different regions and different arc resistances, and the problem of using BP neural network to judge whether the protection is active or not based on real-time impedance measurements is discussed. It is of practical significance to solve the problem that the fault under the arc resistance of the power distribution system cannot accurately measure the fault impedance, which causes the conventional distance protection to fail to operate reliably.
The new computer distance protection method. The method adopts a recursive full-week Fourier algorithm and various compensation methods to perform data preprocessing on the input samples. After considering the characteristics of the circuit when various faults occur, a new type of ground distance and phase distance ratio phase criterion and phase are adopted. A three-layer forward neural network model is established by varying the amount of current difference, and a large number of sample trainings are performed on this model to give correct identification of various faults and abnormal working conditions of the line. This method overcomes the influence of the system operation mode and the transition resistance and other factors, solves the short circuit phenomenon when the system is oscillating, and solves the problem of opening and closing the protection and effectively improves the reliability of the protection operation. Speed ​​relay protection fault classification method. The network uses four-layer feed-forward neural network (FNN) training using BP algorithm. Two kinds of fault classification methods are proposed and two different neural networks are used respectively. One classification for single-phase grounding, two-phase short-circuit, two-phase grounding short-circuit, three-phase short-circuit and three-phase grounding short-circuit faults; another classification for arc faults and non-arc faults in order to implement adaptive automation Reclosing.
Simulation shows that the fault classification using this method is fast and reliable. It also introduces the specific implementation of the neural network used and its specific application in fault detection, fault direction identification, and other aspects.
Application of Multilayer Feedforward Neural Network and Kohrnm Network in Fault Type Identification
The identification of magnetizing inrush currents in transformer protection has been a thorny issue that has plagued relay protection researchers. Based on the artificial neural network, a three-layer feedforward neural network model is proposed and established to take into account the characteristics of transformer magnetizing inrush current and fault conditions. It uses EMTP to perform a large number of simulation calculations, and uses the calculation results as training samples to train the established neural network model. The fault status test results of the model show that the established neural network can respond correctly to the fault condition of the transformer.
Pressure fault current and excitation current method. The network adopts BP type feed-forward neural network (FNN) to distinguish transformer fault current and excitation current by identifying the current waveform. In order to improve the calculation speed, the transfer function of the neuron is selected as the S (Sigmoid) function during training, and after the training, it is changed to a step function. The inrush current training samples are randomly generated in the laboratory by switching a small transformer. The fault current training samples are generated by the simulation software.
2 Research direction and main content of adaptive protection Dedicated to a kind of Kimber artificial release network for high-skilled and intelligent technology and signal processing. Fang Li is now protective. Bookmark3 adaptive relay protection can overcome the same type of traditional protection that has existed for a long time. The difficulties and problems improve the protective performance of the action. At present, adaptive protection is still in the early stages of research and development, but its research results have demonstrated its superiority. The basic requirements for adaptive relay protection are the automatic diagnosis and identification of the system operation mode and fault type, and the adaptive adjustment of the protection action settings and characteristics. With the development of power systems, the system operation methods and types of faults have become more and more complex. Adaptive protection must use a variety of artificial intelligence techniques and signal processing methods to effectively extract fault features, and to achieve automatic recognition of system operating modes and fault types. On this basis, full use of artificial intelligence technology self-learning and self-adaptive capabilities, according to the system's different operating conditions, adaptive adjustment of various protection settings and protection of the operating characteristics. The key to achieving these goals is to select and use appropriate fault information to achieve adaptive protection, as well as the selection and use of Lu Zhengjun. Microcomputers Bus Protection Method of Bus Running Mode PowerSystems, Ge Yaozhong. Adaptive relay protection and its prospects J. Power system He Penteng, Jin Huayu. Energy direction protection principles and characteristics. Chinese Journal of Electrical Engineering, 1997, Yuan Rongxiang, Chen Deshu. Research on New Differential Protection of High Voltage Transmission Lines . Chinese Journal of Electrical Engineering, 2000, 20(4):9-13. He Penteng, Jin Huayu. The realization and test of energy direction protection. Automation of Electric Power System, 199721 (3) 36-38. Luo Ke, He Jia Li. Application of Real-time Communication in EHV Multi-loop Bus Protection. Chinese Journal of Electrical Engineering, 199919 (4) 1-1-3. Power Plant Equipment Automation. Relay Quan Yusheng, Yang Minzhong, Wang Xiaorong, et al. Adaptive Line Parameters Online Estimation in Double Terminal Ranging, 1J Power System Automation, 2000,. Power System Automation 2000
China Built In Gas Oven, Gas Oven ,Gas Stove Oven Supplier
for this kind of goods ,we use good quality stainless steel with high quality GAS STOVE owen .
China Built In Gas Oven,Gas Oven supplier & manufacturer, offer low price, high quality Gas Stove Oven,Gas Oven With Stove, etc.
We support like this kind of goods to different coutnry for more than 20 years ,we had good experience .with good quality and competition price .
Built In Gas Oven,Gas Oven,Gas Stove Oven,Gas Oven With Stove
GAS OWEN
Built In Gas Oven,Gas Oven,Gas Stove Oven,Gas Oven With Stove
GUANGZHOU AIJINGSI TRADING LIMITED , https://www.aichugashob.com